CoreCognition Image only Intentionality: leaderboard
CoreCognition Image only Intentionality — CoreCognition native component accuracy and reported mean. Image+Video, image-only and single-image populations are separate; no pooling or replacement across cohorts. Metric: Accuracy (%). Source: https://grow-ai-like-a-child.github.io/CoreCognition/leaderboard
Metric: Accuracy (%). Source: grow-ai-like-a-child.github.io. Saturation forecast: Rough model projection: around 2026. 77 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Step-1.5V-mini | 86.03 | #2720 |
| 2 | GLM-4V-Plus | 84.21 | #1400 |
| 3 | step-1o-turbo-vision | 83.1 | |
| 4 | NVLM-D-72B | 81.11 | #2181 |
| 5 | Molmo-72B-0924 | 80.56 | #5272 |
| 6 | omchat | 79.76 | |
| 7 | Cambrian-34B | 79.68 | #5295 |
| 8 | Ovis1.6-Gemma2-27B | 78.1 | #1833 |
| 9 | Bunny-Llama3-8B | 77.78 | #7560 |
| 10 | step-1v-32k | 77.06 | |
| 11 | Cambrian-13B | 76.59 | #7053 |
| 12 | GLM-4V-9B | 76.51 | #3333 |
| 13 | parrot-14B | 76.51 | |
| 14 | Reka Core | 76.35 | #3349 |
| 15 | points-qwen-2.5-7B-chat | 76.27 |
Interactive version: theaggregate.ai/benchmark?slug=corecognition-image-only-intentionality · How It Works · Data refreshed daily, snapshot 2026-11-16.